<![CDATA[The rapid development of fiber-optic–based internet technology has led to an increasing demand for stable and evenly distributed WiFi networks. Although internet service providers such as XYZ have established extensive fiber-optic infrastructure, challenges in WiFi access point distribution remain common, particularly regarding uneven network coverage and limited data-driven analysis. These issues raise the question of how to determine optimal WiFi deployment locations to ensure consistent service quality. Therefore, this study aims to analyze the spatial distribution patterns of XYZ’s WiFi network based on fiber-optic connection points, apply the Extreme Gradient Boosting (XGBoost) algorithm to classify the feasibility of WiFi distribution, and evaluate the performance of the proposed model in improving network distribution efficiency. This research employs XGBoost as a classification method to predict suitable and unsuitable WiFi deployment locations using customer data connected via fiber-optic cables. The study focuses on data preprocessing, model construction using XGBoost, performance evaluation in classifying feasible and non-feasible locations, and data balancing techniques to address class imbalance. The dataset consists of 193 XYZ customer records, divided into 80% training data and 20% testing data. The results demonstrate that the XGBoost algorithm achieves high classification accuracy in WiFi network distribution. Consequently, the proposed model can serve as a data-driven recommendation tool for optimizing WiFi deployment, enabling service providers to deliver more evenly distributed, stable, and efficient internet services]]>
